QwenScope
Qwen · Kit
Explore and steer the Qwen3.5-2B language model through sparse autoencoder features: compare two texts' feature activations, or push a feature into generation.…
New
AI research skills and agents
Prompts and agents that read the sources on a question and tell you what each one says.
Categories and filters
Listings
FlyHash vs SimHash Demo
pranamhan · Kit
An interactive browser demo that compares FlyHash and SimHash for retrieving items, built to accompany a paper on FlyHash for LLM agent memory. For researchers…
New
MedCaseAgent
PediaMedAI · Kit
A project page for research resources on rare disease clinical case reports: a 584-record benchmark, a large corpus of case-report metadata and the agent code.…
New
ParsBench Leaderboard
ParsBench · Kit
A leaderboard from ParsBench that scores models on Persian language datasets, with the code to run or adapt your own copy. For Persian NLP researchers and engi…
New
Open VLM Video Leaderboard
opencompass · Kit
A leaderboard of how vision-language models score on video understanding benchmarks, with an overall ranking and a detailed board for each benchmark. For resea…
New
KVPress Leaderboard
nvidia · Kit
Shows a leaderboard that benchmarks KV cache compression methods for language models, using Llama-3.1-8B-Instruct and Qwen3-8B. It suits researchers and engine…
New
Hurricane Wind Speed Regressor
nakulmital · Kit
Predicts hurricane wind speed with a fine-tuned ResNet50 model in a Gradio app. It suits students, researchers and developers who want to see an image regressi…
New
MTEB-BR Leaderboard
MTEB-BR · Kit
Ranks text embedding models on native Brazilian Portuguese tasks, with 93 models scored on 22 tasks. A static leaderboard page for researchers and engineers ch…
New
Open Universal Arabic Asr Leaderboard
msalhab96 · Kit
Compares open-source speech recognition models on Arabic across several dialects, in a Gradio page. For researchers and developers choosing an Arabic speech-to…
New
Next-Concept Modeling WebGPU
mrfakename · Kit
Runs small Next-Concept Modeling checkpoints from Hazy Research in your browser on WebGPU, on TinyStories, LM1B small and Sudoku. It suits researchers and deve…
New
Next-Concept Modeling
mrfakename · Kit
Demonstrates Hazy Research's Next-Concept Modeling, which writes text in parallel from a rough outline to a full sequence, on tasks like summaries, translation…
New
Synthometricon
magnolia-psychometrics · Kit
Search a collection of over 71,000 scales gathered from more than 28,000 tests, surveys and questionnaires. Built for researchers in the behavioral sciences an…
New
Recommend Similar Papers
librarian-bots · Kit
Suggests research papers that are similar to one you already know, using a paper recommendation dataset, in a Gradio app that runs on CPU hardware.
New
RADAR Abdominal CT Demo
junma · Kit
Reads an abdominal CT volume and returns the probability of each of 146 findings across 18 structures, using the RADAR model. A research and teaching demo, not…
New
DFlowNovo De Novo Peptide Sequencing
joelinator · Kit
Predicts peptide sequences from tandem mass spectrometry files with a flow matching model, returning calculated masses and confidence scores, with results you…
New
GeCo2 Object Counting
jerpelhan · Kit
Counts all instances of an object in an image after you mark a few examples, with no retraining or fixed list of classes. Suits researchers and anyone counting…
New
SILVA Aesthetic Scorer
Jannchie · Kit
Scores an uploaded illustration three ways, with one person's taste and two distilled AI judges, each as a number from 0 to 1. Suits artists, dataset curators…
New
FM4M-demo1
ibm-research · Kit
A Gradio demo from IBM Research that names three IBM materials models, smi-ted, selfies-ted and mhg-ged. For researchers and developers who want to look at how…
New
RigidFormer
hugging-apps · Kit
Predicts how several rigid objects move and collide using a Transformer that works on point sets, and shows its rollouts next to simulator ground truth. For ph…
New
PRISM Image to 3D
hugging-apps · Kit
Builds a 3D Gaussian scene from a single picture and shows it in a 3D viewer. It suits researchers and 3D hobbyists who want to try single-image reconstruction…
New
JoyAI Video Edit
hugging-apps · Kit
Edits a video from a plain-language instruction and streams the result back chunk by chunk while it is still being made. A demo of the JoyAI-Video-Edit model f…
New
4DAnyone Multi-View Video
hugging-apps · Kit
Turns one portrait video into synchronized videos of the same performance from several camera views. A demo of the 4DAnyone model for researchers building 4D r…
New
DA-2
haodongli · Kit
Runs the DA^2 depth model in a browser demo, the official demo of Depth Anything in Any Direction. For researchers and developers who want to try depth estimat…
New
THX-02
HAL-X-AI · Kit
Gives a probability for every option of a question you ask about a described situation, using the THX-02 decision model, with an optional thinking mode. A Grad…
New
HAKARI-Bench Leaderboard
hakari-bench · Kit
Shows the public results of HAKARI-Bench, a light multilingual information retrieval benchmark, with tables, model comparisons and filters. For researchers and…
New
FOXES - A Framework for Operational X-ray Emission Synthesis
griffingoodwin04 · Kit
Predicts GOES soft X-ray flux from a 7-channel SDO/AIA solar observation you upload as a NumPy file, and returns a composite image and a flux contribution map.…
New
MSEB Leaderboard
google · Kit
A leaderboard page for the Massive Sound Embedding Benchmark, published by Google, built with Gradio. For researchers who compare sound embedding models.
New
DRS-VPT
fulkast · Kit
Finds where a camera image was taken inside a 3-D point cloud, without a starting guess for the pose. Meant for researchers and students who work on camera loc…
New
Wet-Ink
Freedomform · Kit
Animates a decoding method for diffusion language models in your browser, where you change a window size and watch tokens stay editable or freeze. For research…
New
FINAL-Bench Quantum Leaderboard
FINAL-Bench · Kit
Ranks quantum error correction decoders on a shared public test set, and lists published results beside them. An open, neutral benchmark page for quantum compu…
New
CoWTracker
facebook · Kit
Tracks every pixel of an uploaded video through time and draws the motion as colorful trajectories. Suits researchers and anyone studying how things move in fo…
New
OWSM v4
espnet · Kit
Transcribes speech, translates it between languages, identifies the spoken language and decodes long recordings with the OWSM v4 model, with an optional text p…
New
MEMFOF Optical Flow
egorchistov · Kit
Estimates optical flow, the per-pixel motion between video frames, for Full HD video while using little GPU memory, with a Gradio demo and several trained mode…
New
Safety Doesn't Translate
DhruvParmar051 · Kit
Shows side by side how Cohere's Tiny Aya answers before and after a safety repair that needs no retraining, using pre-judged replies from a test set. It suits…
New
Depth Anything 3
depth-anything · Kit
A demo Space for Depth Anything 3, a research model that, going by its title, recovers a scene's spatial structure from images shot from any viewpoint. The REA…
New
Sports2d
DavidPagnon · Kit
Works out a person's 2D body pose and joint angles from a video file or a webcam feed, in a Gradio page. It suits coaches, movement researchers and anyone stud…
New
Text Surprisal Editor
build-small-hackathon · Kit
Colors each word of your text by how unexpected a tiny 4M-parameter language model finds it. The model has no Transformer blocks. A hackathon project for write…
New
Open Chinese LLM Leaderboard
BAAI · Kit
A leaderboard of large language models for Chinese, run by BAAI as a Gradio Space with datasets for requests and results. For researchers and teams comparing m…
New
Speech analysis
audeering · Kit
Runs two audEERING wav2vec2 models on a speech recording, one for emotion and one for age and gender, and ships four sample clips to try. A Gradio demo for spe…
New
Vevo for Zero-shot VC, TTS, and More
amphion · Kit
Imitates a voice from a reference clip without training on that speaker, for voice conversion and text-to-speech. A demo of the Vevo model from the Amphion pro…
New
Visual Saliency Prediction
alexanderkroner · Kit
Predicts which parts of an image draw the eye first, using the MSI-Net model from a 2020 Neural Networks paper. For researchers and designers who want a quick…
New
Fracture Check
akinchanJain7 · Kit
Screens hand, arm, leg, hip and shoulder X-rays for possible fractures, shows a heatmap of where the model looked, and marks the likely break. A student resear…
New
SchemeArena
launch · Kit
Presents a research project that tests LLM agents for scheming across 400 scenarios, with a monitor called SCOUT. It is a static project page for AI safety res…
New
Saudi SALLM Q9B V1 Demo
Dr-Zeyad-Alghamdi · Kit
Runs a Gradio research demo of a private adapter on the Qwen3.5-9B language model from a browser page, for people who test models on GPU hardware.
New
Saudi SALLM A7B V1 Demo
Dr-Zeyad-Alghamdi · Kit
Lets you try a research language model adapter on top of ALLaM-7B-Instruct-preview from a browser page, for people who test and compare language models.
New
Model Pulse
tardellirs · Kit
Shows daily download history, likes and derivative families for models on the Hugging Face Hub since July 2024, with a model comparison chart and weekly rankin…
New
Open VLM Leaderboard
opencompass · Kit
Shows leaderboards of vision-language model scores gathered with the VLMEvalKit toolkit, with an overall ranking and separate tables for each benchmark. It sui…
New
S1MB Leaderboard
hotchpotch · Kit
Compares System One Decision Models across more than 100 benchmarks, in a viewer of saved results. For researchers who want to see where a model does well or f…
New
Coilstellaration Bench
proxima-fusion · Kit
Scores ONNX models that predict a stellarator's coilset from a plasma boundary and requirement metrics, so researchers can submit models and compare their resu…
New
Heretic Grimoire
heretic-org · Kit
Keeps a searchable archive of the reproduction records that Heretic-generated models publish, with CSV download. For researchers who track or rebuild such mode…
New